Skip to main content
Glama
Sign In
devonthink3-mcp

devonthink3-mcp

by waylake
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

dt3_search

Read-onlyIdempotent

Search a permitted DEVONthink database using native query syntax to find records by metadata, then paginate results in native order. Use read_text to retrieve document content.

Instructions

Search one permitted database with native DEVONthink query syntax, e.g. name:report or tag:review. Metadata only; use read_text for content. Live pagination follows native result order.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "database_uuid": "<database_uuid>",
      "query": "<query>"
    },
    "name": "dt3_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
queryYes
offsetNo
recursiveNo
group_uuidNoRecord UUID or x-devonthink-item:// link. Link page/search parameters are ignored.
database_uuidYes

Output Schema

NameRequiredDescriptionDefault
kindNo
recordsYes
advisoryNo
snapshotYes
next_offsetYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.3.0
    • changedInput schema / properties / limit / maximum
      Previous value: -100New value: +200
  2. First observedv0.2.0

TDQS

A3.8/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds two genuinely useful facts beyond that: results are metadata-only, and 'live pagination follows native result order' warns that ordering is not user-controlled and result sets may shift across pages. It does not state rate limits, permission requirements, or result-count behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, each doing distinct work: capability plus syntax, the sibling boundary, then the pagination caveat. Nothing is repeated from the schema or annotations and the key constraint is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return-value detail is rightly omitted, and the description covers scope, query dialect, and pagination semantics. The remaining gap is the undocumented 'recursive' flag and the exact meaning of the database_uuid permission constraint, which an agent would want before calling.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 17%, so the description carries real weight and it does explain the most important parameter, query, by naming the DEVONthink syntax and giving examples the schema (plain string, 1-2000 chars) does not. However, 'recursive' (default true) and 'database_uuid' scope semantics are left uninterpreted, and 'one permitted database' is the only hint about database_uuid behavior.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Search one permitted database') and pins down the query dialect with concrete examples ('name:report or tag:review'). It draws a clean boundary against dt3_read_text ('Metadata only; use read_text for content'), though it does not distinguish itself from other metadata retrieval siblings such as dt3_get_records or dt3_related.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit when-to-use (native query-syntax search over metadata) and an explicit when-not/alternative (content lookups go to read_text). No exclusions are stated for the remaining siblings, so it stops short of full routing guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools